Quantitative CT Texture Analysis of COVID-19 Hospitalized Patients during 3-24-Month Follow-Up and Correlation with Functional Parameters

Abstract

Background: To quantitatively evaluate CT lung abnormalities in COVID-19 survivors from the acute phase to 24-month follow-up. Quantitative CT features as predictors of abnormalities' persistence were investigated.

Methods: Patients who survived COVID-19 were retrospectively enrolled and underwent a chest CT at baseline (T0) and 3 months (T3) after discharge, with pulmonary function tests (PFTs). Patients with residual CT abnormalities repeated the CT at 12 (T12) and 24 (T24) months after discharge. A machine-learning-based software, CALIPER, calculated the CT percentage of the whole lung of normal parenchyma, ground glass (GG), reticulation (Ret), and vascular-related structures (VRSs). Differences (Δ) were calculated between time points. Receiver operating characteristic (ROC) curve analyses were performed to test the baseline parameters as predictors of functional impairment at T3 and of the persistence of CT abnormalities at T12.

Results: The cohort included 128 patients at T0, 133 at T3, 61 at T12, and 34 at T24. The GG medians were 8.44%, 0.14%, 0.13% and 0.12% at T0, T3, T12 and T24. The Ret medians were 2.79% at T0 and 0.14% at the following time points. All Δ significantly differed from 0, except between T12 and T24. The GG and VRSs at T0 achieved AUCs of 0.73 as predictors of functional impairment, and area under the curves (AUCs) of 0.71 and 0.72 for the persistence of CT abnormalities at T12.

Conclusions: CALIPER accurately quantified the CT changes up to the 24-month follow-up. Resolution mostly occurred at T3, and Ret persisting at T12 was almost unchanged at T24. The baseline parameters were good predictors of functional impairment at T3 and of abnormalities' persistence at T12.

Keywords: COVID-19 pneumonia; CT; follow-up; lung; machine learning; quantitative computed tomography; texture analysis.

Figure 1

The flow chart adopted for the standardized follow-up of COVID-19 discharged patients.

Figure 2

The number of patients for each time point from baseline to T24.

Figure 3

CALIPER analysis of a CT scan of an 84-year-old male patient at T0 (left) and T3 (right). From the upper to the bottom: axial CT slice, axial CALIPER-derived color image overlays (dark and light green = Norm, yellow = GG, orange Ret), the glyph of the lung parenchymal patterns and the 3D volume rendering reconstructions of lung vessels. Compared to the baseline, after three months, most of the abnormalities are resolved, both GG and Ret. A reduction in the VRS is also demonstrated in the 3D volume rendering.

Figure 4

CALIPER analysis of a CT scan of a 92-year-old male patient with right hemidiaphragm elevation and right lower lobe collapse at T0, T12 and T24, from the left to the right. From the upper to the bottom: axial CT slice, axial CALIPER-derived color image overlays (dark and light green = Norm, yellow = GG, orange Ret), the glyph of the lung parenchymal patterns and the 3D volume rendering reconstructions of lung vessels. At T0, the patient presented diffuse areas of GG and Ret. At T12, most of the abnormalities had resolved, while areas of GG associated with Ret persisted, predominantly on the left; these findings persisted also at T24.

Figure 5

ROC curves for the GG (A) and VRS (B) measured at T0, considering TLC impairment at T3 as the outcome, with an AUC of 0.73.

Figure 6

ROC curves for the VRS (A) and GG (B) at T0, considering the enrollment for CT at T24 as outcome.